This content originally appeared on DEV Community and was authored by tryhendri
This is a submission for the Twilio Challenge
What I Built
The Front Desk and Housekeeping are crucial elements in hotel operations. The Front Desk is the first point of contact for guests, while Housekeeping handles various operational situations throughout their stay.
To enhance our service, we aim to integrate AI support into our messaging system. At this stage, the scope of the project includes the following:
- The system will not be integrated with the property management system to retrieve reservation information.
- The messaging chat will only handle guest requests and complaints.
AI will assist the Front Desk by streamlining their tasks. It will help respond to guest inquiries and determine whether to categorize them as requests or complaint
Demo
we will utilize the source from https://github.com/vercel-labs/gemini-chatbot
npx degit vercel-labs/gemini-chatbot whatsappbot-hotelier.
code is here:
An open-source AI chatbot app template built with Next.js, the Vercel AI SDK, Google Gemini, and Vercel KV
Features · Model Providers · Deploy Your Own · Running locally · Authors
Features
- Next.js App Router
- React Server Components (RSCs), Suspense, and Server Actions
- Vercel AI SDK for streaming chat UI
- Support for Google Gemini (default), OpenAI, Anthropic, Cohere, Hugging Face, or custom AI chat models and/or LangChain
-
shadcn/ui
- Styling with Tailwind CSS
- Radix UI for headless component primitives
- Icons from Phosphor Icons
- Chat History, rate limiting, and session storage with Vercel KV
- NextAuth.js for authentication
Model Providers
This template ships with Google Gemini models/gemini-1.0-pro-001 as the default. However, thanks to the Vercel AI SDK, you can switch LLM providers to OpenAI, Anthropic, Cohere, Hugging Face, or using LangChain with just a few lines of code.
Deploy Your Own
You can deploy your…
Unfortunately, the code has not yet been fully implemented. However, here is the structure of the current code:
!(https://dev-to-uploads.s3.amazonaws.com/uploads/articles/dkg6224pnnz6unitaxdc.png)
and table list as below
- ROOM
- USER
- GUEST
- COMPLAINT
- REQUEST
- MESSAGE
- THREAD
Twilio and AI
Using Twilio and AI will be an excellent choice for managing communication between guests and hoteliers.
When a message is received from a guest via Twilio, either through SMS or WhatsApp, it is processed by our AI-powered messaging system. The chatbot will generate a possible response before sending it back to the guest, The Front Desk still needs to evaluate the appropriate response, it will be a training period for making the response more robust, in the future we will remove this step. If the message contains a request, the system will call the appropriate API to create a request. If it contains a complaint, it will call the API to log a complaint. Both requests and complaints will be logged and handled by the Housekeeping team.
Guest (Sends Message)
|
| (Via Twilio SMS/WhatsApp)
|
v
Message System with AI (Chatbot)
|
| (Receives Message)
|
v
(Analyze Message Content)
|
|---> (Contains Request?) --> Yes --> Call Create Request API
| |
| | (Request Created)
| |
| |
| |
| |
| |
|---> (Contains Complaint?) --> Yes --> Call Create Complaint API
| |
| | (Complaint Created)
| |
| |
| |
| |
| |
|
v
(Prepare Response)
|
| (Based on Analysis and API Results)
|
v
(Send Response Back to Guest)
|
| (Via Twilio SMS/WhatsApp)
|
v
Guest (Receives Response)
This content originally appeared on DEV Community and was authored by tryhendri
tryhendri | Sciencx (2024-06-24T00:02:22+00:00) Leverage AI with Twilio for Hotelier. Retrieved from https://www.scien.cx/2024/06/24/leverage-ai-with-twilio-for-hotelier/
Please log in to upload a file.
There are no updates yet.
Click the Upload button above to add an update.